30 results about "Space-occupying lesion" patented technology

The invention discloses a tumor malignant risk stratification auxiliary diagnosis system of an artificial intelligence medical image. The system comprises a data acquisition module, a data preprocessing module, a model establishment module, a model verification and optimization module, a stratification diagnosis module and a database platform. The tumor malignant risk stratification auxiliary diagnosis system of the invention is based on artificial intelligence technology, successive stratification of the malignant risk of the tumor can be achieved, the clinical diagnosis thinking is simulated, based on the high-precision ability of detecting benign lesions and malignant tumors of artificial intelligence model, and the space-occupying lesions with definite imaging features are diagnosed automatically. As a result, the system can substantially assist the clinical management decision of space-occupying lesions, improve the existing work flow of clinical diagnosis, increase the confidenceof doctors in diagnosis, reduce the work pressure, reduce the anxiety of patients with low-risk malignant lesions, greatly improve the diagnostic rate of benign lesions and malignant tumors, and hopefully realize the landing implementation of artificial intelligence clinical auxiliary diagnosis.

The invention discloses a liver ultrasonic image identification method based on sparse expression. The method comprises the following steps of: (1) selecting an interested area from a liver ultrasonic image training sample with a space-occupying lesion area; (2) extracting a gray scale symbiosis matrix texture ratio characteristic, a fractal characteristic and a abrupt change rate characteristic of the interested area; (3) utilizing a dictionary expansion method based on sparse reconstruction to construct an expanded dictionary by the image characteristics obtained in the step (2); (4) utilizing the expanded dictionary obtained in the step (3) to construct a classifier based on sparse expression; and (5) inputting the image characteristics of a testing sample into the classifier for identification and judgment, and identifying out the liver ultrasonic image with the space-occupying lesion area. According to the invention, the classified identification accuracy is high, and each index accords with a clinical diagnosis range.

The invention provides a liver space-occupying lesion identification method and device and an implementation device, which relate to the technical field of medical images. The method comprises the steps of acquiring a first CT image; recognizing the first CT image of each phase by a first recognition model, and recognizing the suspected focus position of the first CT image of each phase; carryingout the lateral and longitudinal combination of suspect lesion positions to obtain a detection frame position, and cutting that first CT image of each phase longitudinally according to the detection frame position to obtain a second CT image; identifying the lesion type of the suspected lesion position in the second CT image through the second recognition model, and judging the target lesion position from the suspected lesion position; segmenting the first CT image by the third recognition model, and obtaining the third CT image; and according to the detection frame on the third CT image, obtaining the position coordinates of the target focus. The lateral features between the four-phase images and the longitudinal features of the single-phase images are comprehensively considered, which greatly improves the accuracy of the recognition results.

The invention relates to the technical field of medicines and aims at solving the technical problem about providing a new effective choice for preventing or treating intracranial space occupying lesion and intracranial tissues and organs inflammation. The scheme for solving the technical problem provides an application of Honokiol to preparing drugs for preventing or treating intracranial space occupying lesion and intracranial tissues and organs inflammation. The invention further provides the application of Honokiol combined with carmustine (BCNU) to preventing or treating primary or metastatic tumors of brain, and the application prospect is bright.

The invention relates to a traditional Chinese medicinal extract product prepared from traditional Chinese medicinal raw materials composed of root of large-flowered skullcap, cape jasmine and pseudo-ginseng, a traditional Chinese medicinal composition containing scutelloside, geniposide and panax notoginseng saponins, a medicine containing the traditional Chinese medicinal extract product or the traditional Chinese medicinal composition, and their clinical application. The traditional Chinese medicinal extract product, the traditional Chinese medicinal composition and the medicine containing the traditional Chinese medicinal extract product or the traditional Chinese medicinal composition can be used in emergency treatment and treatment of diseases such as cerebrovascular disease, intracranial infection, craniocerebral trauma, craniocerebral space-occupying lesion or intoxication and the like, which are mainly represented by brain edema.

When an image for PET attenuation correction is generated from an MR image, the MR image captured by MRI is segmented into regions according to pixel values. In a region in which a radiation attenuation coefficient is considered to be uniform, a radiation attenuation correction value is determined by referring to an existing radiation attenuation correction value table. In a region including multiple tissues having different radiation attenuation coefficients, a radiation attenuation correction value is determined by referring to a standard image. In such a manner, an image for PET attenuation correction in which tissues having similar pixel values in the MR image but different attenuation coefficients for radiation can be distinguished and that can accommodate individual differences and an affected area such as a space occupying lesion (for example, a cancer, abscess, or the like) and an organic defect is generated.

The invention discloses an electrode depolarization device, the technical problem needs to be solved is to carry out the depolarization processing to the electrode which has the polarization phenomenon. The electrode depolarization device of the invention is provided with a DC power supply and an electrolytic cell, the interior of the electrolytic cell is filled with electrolyte, a positive electrode of the DC power supply is connected with an electrode lead adapter device, the electrode to be subject to the depolarization processing which is connected with the electrode lead adapter device and a cathode which is connected with a negative electrode of the DC power supply are immersed in the electrolyte. Compared with the prior art, the connection structure of the electrode to be subject to the depolarization processing which is connected with the electrode lead adapter device and the cathode which is connected with the negative electrode of the DC power supply is immersed in the electrolyte, so the depolarization processing of an electroencephalogram silver or sliver-silver chloride electrode which has the polarization phenomenon can be carried out, thereby improving the measurement quality of the electroencephalogram and the electrocardiogram and improving the diagnosis accuracy of the doctors on epilepsy, brain trauma, encephalitis, cerebrovascular diseases, intracranial space occupying lesions, heart diseases, and so on.

The invention relates to a renal cancer exosome marker group and application thereof. The marker group comprises mRNA of an exosome-derived VHL gene, mRNA of an exosome-derived PBRM1 gene, mRNA of anexosome-derived ATM gene, mRNA of an exosome-derived PTEN gene and mRNA of an exosome-derived SETD2 gene. By means of detection of the mRNAs of the exosome-derived VHL, PBRM1, ATM, PTEN and SETD2 genes and a corresponding diagnosis model, the distinction between renal cancer patients and non-renal cancer patients can be achieved, especially the distinction between early renal cancer samples (suchas clinical T1 renal cancer) and non-renal cancer samples (for example, normal people, simple renal cysts, hamartomas and other benign renal space occupying lesions), and the defect is overcome that early renal cancer is clinically difficult to accurately diagnose in time.

The invention discloses a new application of a normal saline injection in identifying benignity or malignancy of tiny space occupying lesion in liver. The conventional normal saline injection is utilized to achieve unexpected effects. The normal saline injection has high identification sensitivity and specificity, and can be used for clarify a diagnosis on the benignity or malignancy of a tiny space occupying lesion in the liver.

The invention discloses a traditional Chinese medicine composition for treating space occupying lesions, which is prepared from the following raw materials in parts by weight: 4-8 parts of white mustard seed, 15-25 parts of medcinal evodia fruit, 5-10 parts of pinellia tuber, 4-8 parts of Szechuan lovage rhizome, 6-10 parts of earthworm, 10-20 parts of pilose asiabell root, 15-25 parts of ginger, and 25-35 parts of jujube. The traditional Chinese medicine composition for treating space occupying lesions provided in the invention solves the problems of poor treatment effect on space occupying lesions, difficulty in effecting a radical cure, and high possibility of causing other lesions in the prior art.

The invention aims to provide an electric excision biopsy device for a sheath of a fiberoptic ductoscopy, so as to excise a space occupying lesion in a laticifer with an electric knife. The electric excision biopsy device is characterized in that the electric excision biopsy device consists of the sheath and the electric knife, wherein the sheath adopts a pipe-shaped structure of which the sectionis circular or elliptic, and the front end of the sheath adopts a bevel structure; the electric knife penetrates across the bevel structure at the front end of the sheath or is in arc-shaped coincidence with a low-point position of the bevel structure; two ends of the electric knife are connected with the sheath; the electric knife is located on one side in a lower position of the bevel at the front end of the sheath; and the electric knife is connected with a sheath external power source through a conducting wire.

The invention relates to a pair of intra-operative intelligent navigation glasses for precisely cutting away intracranial space-occupying lesions. The pair of glasses includes a glasses body, an imagetransmission module, a central processing module and a display module; the glasses body comprises lenses, a glasses frame, glasses legs and a polymer lithium battery; the image transmission module can receive patient two-dimensional image data sent by a wireless terminal; the central processing module rebuilds the two-dimensional image data to obtain a three-dimensional depth image, and the transparency of the image is improved; the display module is used for displaying the three-dimensional depth image. Due to the fact that the three-dimensional depth image can display the lesion position, after a surgeon wears the pair of intelligent glasses, the image is adopted as a background, the built anfractuosity, gyrus, blood vessels and other structures in the image are compared with the surgery field actual anatomical structure, the surgery field reality scene can be enhanced, the lesion position can be determined, and then surgery is guided. The pair of glasses is high in precision, reasonable in design, easy to obtain, simple in structure, low in price and applicable to precisely cutting away the meningiomas and other intracranial space-occupying lesions.

The invention belongs to the technical field of medical treatment, and particularly relates to a physical examination recommendation method and device for space occupying lesions, equipment and a storage medium. The method comprises the following steps: acquiring image description text' segmenting the image description text into text information of a target object; according to the text information of the target object, utilizing a preset label set to extract position occupying lesion feature information of the target object, wherein the preset label set is composed of all position occupying lesion features of the target object; according to the extracted feature information and a feature recommendation dictionary, performing calculation to obtain a first recommendation value of the target object space occupying lesion, wherein the feature recommendation dictionary comprises the corresponding relation between the target object space occupying lesion feature information and the recommendation probability; and when the first recommendation value of the position occupying lesion of the target object exceeds the recommendation threshold value, recommending a physical examination item of the target object to the user. The method improves the accuracy of information extraction, and then improves the accuracy and reliability of physical examination item recommendation.

The invention provides a method for detectingmulti-site mutation of free DNA of lung tumor plasma. The method is characterized in that a specific primer, a specific PNA probe and a capture technology are adopted to improve ctDNA detection and specificity, so that trace ctDNA can be detected. The invention provides primers, probes and a detection method for gene variation detection in a peripheral blood sample of a lung space-occupying lesion patient. The method has the advantages of high sensitivity, strong specificity, good repeatability, simplicity in operation, rapidness in detection, safety and the like, and has an auxiliary effect on diagnosis of lung cancer.